Adapt session model selection to the slash/input/session architecture

- host trio kept on the merged api-proxy: session.models (provider-grouped
  advisory directory), session.selectModel (validated provider, advisory
  model), installAgentLlmTarget threaded through create/resume/ensureSession;
  the gateway declares the llm inject it reads
- history no longer piggybacks modelTarget: the current target travels on
  session.models alone (the /model popup is the sole consumer)
- new @deepseek-ai/dsh-client-ui-model plugin: /model popupSelect over the
  wire — options load the directory (group label in the detail column,
  provider-local failures listed inline), onSelect routes selectModel;
  failures ride the popup shell's error/retry surface
- ModelSelector package, conversation.composer.control slot, and the
  Session-side modelSelection state machine are removed: model selection
  belongs to the /model popup; the named conversation.input.model seat
  stays empty until a control-seat entry is designed for it

packages/host/apiproxy/src/api/sessions.ts

@@ -129,7 +129,7 @@ export interface SessionsApi {
    * rebuilds the surface from the events with the shared fold.
    */
   history(request: RpcRequest<{ sessionId: SessionId; beforeSeq?: number; maxMessages?: number }>):
-  Promise<RpcResponse<{ events: HistoryEntry[]; hasMore: boolean; modelTarget: ModelTarget }>>
+  Promise<RpcResponse<{ events: HistoryEntry[]; hasMore: boolean }>>
 
   /** Reads a fresh advisory model directory for this session. Provider lookups run independently. */
   models(request: RpcRequest<{ sessionId: SessionId }>): Promise<RpcResponse<SessionModels>>